diff options
Diffstat (limited to 'virt')
-rw-r--r-- | virt/kvm/Kconfig | 3 | ||||
-rw-r--r-- | virt/kvm/arm/arch_timer.c | 171 | ||||
-rw-r--r-- | virt/kvm/arm/arm.c | 158 | ||||
-rw-r--r-- | virt/kvm/arm/hyp/timer-sr.c | 48 | ||||
-rw-r--r-- | virt/kvm/arm/hyp/vgic-v2-sr.c | 5 | ||||
-rw-r--r-- | virt/kvm/arm/mmio.c | 6 | ||||
-rw-r--r-- | virt/kvm/arm/mmu.c | 76 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-init.c | 8 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-irqfd.c | 3 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-its.c | 8 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-mmio.c | 115 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-v2.c | 29 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-v3.c | 31 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-v4.c | 8 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic.c | 49 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic.h | 8 | ||||
-rw-r--r-- | virt/kvm/kvm_main.c | 70 |
17 files changed, 543 insertions, 253 deletions
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 70691c0..cca7e06 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -51,3 +51,6 @@ config KVM_COMPAT config HAVE_KVM_IRQ_BYPASS bool + +config HAVE_KVM_VCPU_ASYNC_IOCTL + bool diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 4151250..70268c0 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -93,19 +93,21 @@ static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id; struct arch_timer_context *vtimer; - if (!vcpu) { - pr_warn_once("Spurious arch timer IRQ on non-VCPU thread\n"); - return IRQ_NONE; - } - vtimer = vcpu_vtimer(vcpu); + /* + * We may see a timer interrupt after vcpu_put() has been called which + * sets the CPU's vcpu pointer to NULL, because even though the timer + * has been disabled in vtimer_save_state(), the hardware interrupt + * signal may not have been retired from the interrupt controller yet. + */ + if (!vcpu) + return IRQ_HANDLED; - if (!vtimer->irq.level) { - vtimer->cnt_ctl = read_sysreg_el0(cntv_ctl); - if (kvm_timer_irq_can_fire(vtimer)) - kvm_timer_update_irq(vcpu, true, vtimer); - } + vtimer = vcpu_vtimer(vcpu); + if (kvm_timer_should_fire(vtimer)) + kvm_timer_update_irq(vcpu, true, vtimer); - if (unlikely(!irqchip_in_kernel(vcpu->kvm))) + if (static_branch_unlikely(&userspace_irqchip_in_use) && + unlikely(!irqchip_in_kernel(vcpu->kvm))) kvm_vtimer_update_mask_user(vcpu); return IRQ_HANDLED; @@ -231,6 +233,16 @@ static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx) { u64 cval, now; + if (timer_ctx->loaded) { + u32 cnt_ctl; + + /* Only the virtual timer can be loaded so far */ + cnt_ctl = read_sysreg_el0(cntv_ctl); + return (cnt_ctl & ARCH_TIMER_CTRL_ENABLE) && + (cnt_ctl & ARCH_TIMER_CTRL_IT_STAT) && + !(cnt_ctl & ARCH_TIMER_CTRL_IT_MASK); + } + if (!kvm_timer_irq_can_fire(timer_ctx)) return false; @@ -245,15 +257,7 @@ bool kvm_timer_is_pending(struct kvm_vcpu *vcpu) struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); - if (vtimer->irq.level || ptimer->irq.level) - return true; - - /* - * When this is called from withing the wait loop of kvm_vcpu_block(), - * the software view of the timer state is up to date (timer->loaded - * is false), and so we can simply check if the timer should fire now. - */ - if (!vtimer->loaded && kvm_timer_should_fire(vtimer)) + if (kvm_timer_should_fire(vtimer)) return true; return kvm_timer_should_fire(ptimer); @@ -271,9 +275,9 @@ void kvm_timer_update_run(struct kvm_vcpu *vcpu) /* Populate the device bitmap with the timer states */ regs->device_irq_level &= ~(KVM_ARM_DEV_EL1_VTIMER | KVM_ARM_DEV_EL1_PTIMER); - if (vtimer->irq.level) + if (kvm_timer_should_fire(vtimer)) regs->device_irq_level |= KVM_ARM_DEV_EL1_VTIMER; - if (ptimer->irq.level) + if (kvm_timer_should_fire(ptimer)) regs->device_irq_level |= KVM_ARM_DEV_EL1_PTIMER; } @@ -286,7 +290,8 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_ctx->irq.irq, timer_ctx->irq.level); - if (likely(irqchip_in_kernel(vcpu->kvm))) { + if (!static_branch_unlikely(&userspace_irqchip_in_use) || + likely(irqchip_in_kernel(vcpu->kvm))) { ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id, timer_ctx->irq.irq, timer_ctx->irq.level, @@ -324,12 +329,20 @@ static void kvm_timer_update_state(struct kvm_vcpu *vcpu) struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + bool level; if (unlikely(!timer->enabled)) return; - if (kvm_timer_should_fire(vtimer) != vtimer->irq.level) - kvm_timer_update_irq(vcpu, !vtimer->irq.level, vtimer); + /* + * The vtimer virtual interrupt is a 'mapped' interrupt, meaning part + * of its lifecycle is offloaded to the hardware, and we therefore may + * not have lowered the irq.level value before having to signal a new + * interrupt, but have to signal an interrupt every time the level is + * asserted. + */ + level = kvm_timer_should_fire(vtimer); + kvm_timer_update_irq(vcpu, level, vtimer); if (kvm_timer_should_fire(ptimer) != ptimer->irq.level) kvm_timer_update_irq(vcpu, !ptimer->irq.level, ptimer); @@ -337,6 +350,12 @@ static void kvm_timer_update_state(struct kvm_vcpu *vcpu) phys_timer_emulate(vcpu); } +static void __timer_snapshot_state(struct arch_timer_context *timer) +{ + timer->cnt_ctl = read_sysreg_el0(cntv_ctl); + timer->cnt_cval = read_sysreg_el0(cntv_cval); +} + static void vtimer_save_state(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; @@ -348,13 +367,12 @@ static void vtimer_save_state(struct kvm_vcpu *vcpu) if (!vtimer->loaded) goto out; - if (timer->enabled) { - vtimer->cnt_ctl = read_sysreg_el0(cntv_ctl); - vtimer->cnt_cval = read_sysreg_el0(cntv_cval); - } + if (timer->enabled) + __timer_snapshot_state(vtimer); /* Disable the virtual timer */ write_sysreg_el0(0, cntv_ctl); + isb(); vtimer->loaded = false; out: @@ -448,8 +466,7 @@ static void kvm_timer_vcpu_load_vgic(struct kvm_vcpu *vcpu) bool phys_active; int ret; - phys_active = vtimer->irq.level || - kvm_vgic_map_is_active(vcpu, vtimer->irq.irq); + phys_active = kvm_vgic_map_is_active(vcpu, vtimer->irq.irq); ret = irq_set_irqchip_state(host_vtimer_irq, IRQCHIP_STATE_ACTIVE, @@ -479,9 +496,6 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) vtimer_restore_state(vcpu); - if (has_vhe()) - disable_el1_phys_timer_access(); - /* Set the background timer for the physical timer emulation. */ phys_timer_emulate(vcpu); } @@ -499,8 +513,8 @@ bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu) vlevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_VTIMER; plevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_PTIMER; - return vtimer->irq.level != vlevel || - ptimer->irq.level != plevel; + return kvm_timer_should_fire(vtimer) != vlevel || + kvm_timer_should_fire(ptimer) != plevel; } void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) @@ -510,9 +524,6 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) if (unlikely(!timer->enabled)) return; - if (has_vhe()) - enable_el1_phys_timer_access(); - vtimer_save_state(vcpu); /* @@ -535,54 +546,27 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) set_cntvoff(0); } -static void unmask_vtimer_irq(struct kvm_vcpu *vcpu) +/* + * With a userspace irqchip we have to check if the guest de-asserted the + * timer and if so, unmask the timer irq signal on the host interrupt + * controller to ensure that we see future timer signals. + */ +static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu) { struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); if (unlikely(!irqchip_in_kernel(vcpu->kvm))) { - kvm_vtimer_update_mask_user(vcpu); - return; - } - - /* - * If the guest disabled the timer without acking the interrupt, then - * we must make sure the physical and virtual active states are in - * sync by deactivating the physical interrupt, because otherwise we - * wouldn't see the next timer interrupt in the host. - */ - if (!kvm_vgic_map_is_active(vcpu, vtimer->irq.irq)) { - int ret; - ret = irq_set_irqchip_state(host_vtimer_irq, - IRQCHIP_STATE_ACTIVE, - false); - WARN_ON(ret); + __timer_snapshot_state(vtimer); + if (!kvm_timer_should_fire(vtimer)) { + kvm_timer_update_irq(vcpu, false, vtimer); + kvm_vtimer_update_mask_user(vcpu); + } } } -/** - * kvm_timer_sync_hwstate - sync timer state from cpu - * @vcpu: The vcpu pointer - * - * Check if any of the timers have expired while we were running in the guest, - * and inject an interrupt if that was the case. - */ void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) { - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - - /* - * If we entered the guest with the vtimer output asserted we have to - * check if the guest has modified the timer so that we should lower - * the line at this point. - */ - if (vtimer->irq.level) { - vtimer->cnt_ctl = read_sysreg_el0(cntv_ctl); - vtimer->cnt_cval = read_sysreg_el0(cntv_cval); - if (!kvm_timer_should_fire(vtimer)) { - kvm_timer_update_irq(vcpu, false, vtimer); - unmask_vtimer_irq(vcpu); - } - } + unmask_vtimer_irq_user(vcpu); } int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) @@ -726,7 +710,7 @@ static int kvm_timer_dying_cpu(unsigned int cpu) return 0; } -int kvm_timer_hyp_init(void) +int kvm_timer_hyp_init(bool has_gic) { struct arch_timer_kvm_info *info; int err; @@ -762,10 +746,13 @@ int kvm_timer_hyp_init(void) return err; } - err = irq_set_vcpu_affinity(host_vtimer_irq, kvm_get_running_vcpus()); - if (err) { - kvm_err("kvm_arch_timer: error setting vcpu affinity\n"); - goto out_free_irq; + if (has_gic) { + err = irq_set_vcpu_affinity(host_vtimer_irq, + kvm_get_running_vcpus()); + if (err) { + kvm_err("kvm_arch_timer: error setting vcpu affinity\n"); + goto out_free_irq; + } } kvm_info("virtual timer IRQ%d\n", host_vtimer_irq); @@ -813,6 +800,19 @@ static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu) return true; } +bool kvm_arch_timer_get_input_level(int vintid) +{ + struct kvm_vcpu *vcpu = kvm_arm_get_running_vcpu(); + struct arch_timer_context *timer; + + if (vintid == vcpu_vtimer(vcpu)->irq.irq) + timer = vcpu_vtimer(vcpu); + else + BUG(); /* We only map the vtimer so far */ + + return kvm_timer_should_fire(timer); +} + int kvm_timer_enable(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; @@ -834,14 +834,15 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu) return -EINVAL; } - ret = kvm_vgic_map_phys_irq(vcpu, host_vtimer_irq, vtimer->irq.irq); + ret = kvm_vgic_map_phys_irq(vcpu, host_vtimer_irq, vtimer->irq.irq, + kvm_arch_timer_get_input_level); if (ret) return ret; no_vgic: preempt_disable(); timer->enabled = 1; - kvm_timer_vcpu_load_vgic(vcpu); + kvm_timer_vcpu_load(vcpu); preempt_enable(); return 0; diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index a67c106..94a36f6 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -71,17 +71,17 @@ static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled); static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu) { - BUG_ON(preemptible()); __this_cpu_write(kvm_arm_running_vcpu, vcpu); } +DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use); + /** * kvm_arm_get_running_vcpu - get the vcpu running on the current CPU. * Must be called from non-preemptible context */ struct kvm_vcpu *kvm_arm_get_running_vcpu(void) { - BUG_ON(preemptible()); return __this_cpu_read(kvm_arm_running_vcpu); } @@ -188,6 +188,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm->vcpus[i] = NULL; } } + atomic_set(&kvm->online_vcpus, 0); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) @@ -294,9 +295,11 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { + if (vcpu->arch.has_run_once && unlikely(!irqchip_in_kernel(vcpu->kvm))) + static_branch_dec(&userspace_irqchip_in_use); + kvm_mmu_free_memory_caches(vcpu); kvm_timer_vcpu_terminate(vcpu); - kvm_vgic_vcpu_destroy(vcpu); kvm_pmu_vcpu_destroy(vcpu); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, vcpu); @@ -381,17 +384,24 @@ static void vcpu_power_off(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { + vcpu_load(vcpu); + if (vcpu->arch.power_off) mp_state->mp_state = KVM_MP_STATE_STOPPED; else mp_state->mp_state = KVM_MP_STATE_RUNNABLE; + vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { + int ret = 0; + + vcpu_load(vcpu); + switch (mp_state->mp_state) { case KVM_MP_STATE_RUNNABLE: vcpu->arch.power_off = false; @@ -400,10 +410,11 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, vcpu_power_off(vcpu); break; default: - return -EINVAL; + ret = -EINVAL; } - return 0; + vcpu_put(vcpu); + return ret; } /** @@ -524,14 +535,22 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) vcpu->arch.has_run_once = true; - /* - * Map the VGIC hardware resources before running a vcpu the first - * time on this VM. - */ - if (unlikely(irqchip_in_kernel(kvm) && !vgic_ready(kvm))) { - ret = kvm_vgic_map_resources(kvm); - if (ret) - return ret; + if (likely(irqchip_in_kernel(kvm))) { + /* + * Map the VGIC hardware resources before running a vcpu the + * first time on this VM. + */ + if (unlikely(!vgic_ready(kvm))) { + ret = kvm_vgic_map_resources(kvm); + if (ret) + return ret; + } + } else { + /* + * Tell the rest of the code that there are userspace irqchip + * VMs in the wild. + */ + static_branch_inc(&userspace_irqchip_in_use); } ret = kvm_timer_enable(vcpu); @@ -619,18 +638,27 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) if (unlikely(!kvm_vcpu_initialized(vcpu))) return -ENOEXEC; + vcpu_load(vcpu); + ret = kvm_vcpu_first_run_init(vcpu); if (ret) - return ret; + goto out; if (run->exit_reason == KVM_EXIT_MMIO) { ret = kvm_handle_mmio_return(vcpu, vcpu->run); if (ret) - return ret; + goto out; + if (kvm_arm_handle_step_debug(vcpu, vcpu->run)) { + ret = 0; + goto out; + } + } - if (run->immediate_exit) - return -EINTR; + if (run->immediate_exit) { + ret = -EINTR; + goto out; + } kvm_sigset_activate(vcpu); @@ -663,19 +691,30 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_vgic_flush_hwstate(vcpu); /* - * If we have a singal pending, or need to notify a userspace - * irqchip about timer or PMU level changes, then we exit (and - * update the timer level state in kvm_timer_update_run - * below). + * Exit if we have a signal pending so that we can deliver the + * signal to user space. */ - if (signal_pending(current) || - kvm_timer_should_notify_user(vcpu) || - kvm_pmu_should_notify_user(vcpu)) { + if (signal_pending(current)) { ret = -EINTR; run->exit_reason = KVM_EXIT_INTR; } /* + * If we're using a userspace irqchip, then check if we need + * to tell a userspace irqchip about timer or PMU level + * changes and if so, exit to userspace (the actual level + * state gets updated in kvm_timer_update_run and + * kvm_pmu_update_run below). + */ + if (static_branch_unlikely(&userspace_irqchip_in_use)) { + if (kvm_timer_should_notify_user(vcpu) || + kvm_pmu_should_notify_user(vcpu)) { + ret = -EINTR; + run->exit_reason = KVM_EXIT_INTR; + } + } + + /* * Ensure we set mode to IN_GUEST_MODE after we disable * interrupts and before the final VCPU requests check. * See the comment in kvm_vcpu_exiting_guest_mode() and @@ -687,7 +726,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_request_pending(vcpu)) { vcpu->mode = OUTSIDE_GUEST_MODE; kvm_pmu_sync_hwstate(vcpu); - kvm_timer_sync_hwstate(vcpu); + if (static_branch_unlikely(&userspace_irqchip_in_use)) + kvm_timer_sync_hwstate(vcpu); kvm_vgic_sync_hwstate(vcpu); local_irq_enable(); preempt_enable(); @@ -731,7 +771,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) * we don't want vtimer interrupts to race with syncing the * timer virtual interrupt state. */ - kvm_timer_sync_hwstate(vcpu); + if (static_branch_unlikely(&userspace_irqchip_in_use)) + kvm_timer_sync_hwstate(vcpu); /* * We may have taken a host interrupt in HYP mode (ie @@ -769,6 +810,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_sigset_deactivate(vcpu); +out: + vcpu_put(vcpu); return ret; } @@ -984,66 +1027,88 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; struct kvm_device_attr attr; + long r; + + vcpu_load(vcpu); switch (ioctl) { case KVM_ARM_VCPU_INIT: { struct kvm_vcpu_init init; + r = -EFAULT; if (copy_from_user(&init, argp, sizeof(init))) - return -EFAULT; + break; - return kvm_arch_vcpu_ioctl_vcpu_init(vcpu, &init); + r = kvm_arch_vcpu_ioctl_vcpu_init(vcpu, &init); + break; } case KVM_SET_ONE_REG: case KVM_GET_ONE_REG: { struct kvm_one_reg reg; + r = -ENOEXEC; if (unlikely(!kvm_vcpu_initialized(vcpu))) - return -ENOEXEC; + break; + r = -EFAULT; if (copy_from_user(®, argp, sizeof(reg))) - return -EFAULT; + break; + if (ioctl == KVM_SET_ONE_REG) - return kvm_arm_set_reg(vcpu, ®); + r = kvm_arm_set_reg(vcpu, ®); else - return kvm_arm_get_reg(vcpu, ®); + r = kvm_arm_get_reg(vcpu, ®); + break; } case KVM_GET_REG_LIST: { struct kvm_reg_list __user *user_list = argp; struct kvm_reg_list reg_list; unsigned n; + r = -ENOEXEC; if (unlikely(!kvm_vcpu_initialized(vcpu))) - return -ENOEXEC; + break; + r = -EFAULT; if (copy_from_user(®_list, user_list, sizeof(reg_list))) - return -EFAULT; + break; n = reg_list.n; reg_list.n = kvm_arm_num_regs(vcpu); if (copy_to_user(user_list, ®_list, sizeof(reg_list))) - return -EFAULT; + break; + r = -E2BIG; if (n < reg_list.n) - return -E2BIG; - return kvm_arm_copy_reg_indices(vcpu, user_list->reg); + break; + r = kvm_arm_copy_reg_indices(vcpu, user_list->reg); + break; } case KVM_SET_DEVICE_ATTR: { + r = -EFAULT; if (copy_from_user(&attr, argp, sizeof(attr))) - return -EFAULT; - return kvm_arm_vcpu_set_attr(vcpu, &attr); + break; + r = kvm_arm_vcpu_set_attr(vcpu, &attr); + break; } case KVM_GET_DEVICE_ATTR: { + r = -EFAULT; if (copy_from_user(&attr, argp, sizeof(attr))) - return -EFAULT; - return kvm_arm_vcpu_get_attr(vcpu, &attr); + break; + r = kvm_arm_vcpu_get_attr(vcpu, &attr); + break; } case KVM_HAS_DEVICE_ATTR: { + r = -EFAULT; if (copy_from_user(&attr, argp, sizeof(attr))) - return -EFAULT; - return kvm_arm_vcpu_has_attr(vcpu, &attr); + break; + r = kvm_arm_vcpu_has_attr(vcpu, &attr); + break; } default: - return -EINVAL; + r = -EINVAL; } + + vcpu_put(vcpu); + return r; } /** @@ -1236,6 +1301,7 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self, cpu_hyp_reset(); return NOTIFY_OK; + case CPU_PM_ENTER_FAILED: case CPU_PM_EXIT: if (__this_cpu_read(kvm_arm_hardware_enabled)) /* The hardware was enabled before suspend. */ @@ -1323,7 +1389,7 @@ static int init_subsystems(void) /* * Init HYP architected timer support */ - err = kvm_timer_hyp_init(); + err = kvm_timer_hyp_init(vgic_present); if (err) goto out; @@ -1502,7 +1568,7 @@ int kvm_arch_init(void *opaque) bool in_hyp_mode; if (!is_hyp_mode_available()) { - kvm_err("HYP mode not available\n"); + kvm_info("HYP mode not available\n"); return -ENODEV; } diff --git a/virt/kvm/arm/hyp/timer-sr.c b/virt/kvm/arm/hyp/timer-sr.c index f398616..f24404b 100644 --- a/virt/kvm/arm/hyp/timer-sr.c +++ b/virt/kvm/arm/hyp/timer-sr.c @@ -27,42 +27,34 @@ void __hyp_text __kvm_timer_set_cntvoff(u32 cntvoff_low, u32 cntvoff_high) write_sysreg(cntvoff, cntvoff_el2); } -void __hyp_text enable_el1_phys_timer_access(void) -{ - u64 val; - - /* Allow physical timer/counter access for the host */ - val = read_sysreg(cnthctl_el2); - val |= CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN; - write_sysreg(val, cnthctl_el2); -} - -void __hyp_text disable_el1_phys_timer_access(void) -{ - u64 val; - - /* - * Disallow physical timer access for the guest - * Physical counter access is allowed - */ - val = read_sysreg(cnthctl_el2); - val &= ~CNTHCTL_EL1PCEN; - val |= CNTHCTL_EL1PCTEN; - write_sysreg(val, cnthctl_el2); -} - void __hyp_text __timer_disable_traps(struct kvm_vcpu *vcpu) { /* * We don't need to do this for VHE since the host kernel runs in EL2 * with HCR_EL2.TGE ==1, which makes those bits have no impact. */ - if (!has_vhe()) - enable_el1_phys_timer_access(); + if (!has_vhe()) { + u64 val; + + /* Allow physical timer/counter access for the host */ + val = read_sysreg(cnthctl_el2); + val |= CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN; + write_sysreg(val, cnthctl_el2); + } } void __hyp_text __timer_enable_traps(struct kvm_vcpu *vcpu) { - if (!has_vhe()) - disable_el1_phys_timer_access(); + if (!has_vhe()) { + u64 val; + + /* + * Disallow physical timer access for the guest + * Physical counter access is allowed + */ + val = read_sysreg(cnthctl_el2); + val &= ~CNTHCTL_EL1PCEN; + val |= CNTHCTL_EL1PCTEN; + write_sysreg(val, cnthctl_el2); + } } diff --git a/virt/kvm/arm/hyp/vgic-v2-sr.c b/virt/kvm/arm/hyp/vgic-v2-sr.c index a3f18d3..4fe6e79 100644 --- a/virt/kvm/arm/hyp/vgic-v2-sr.c +++ b/virt/kvm/arm/hyp/vgic-v2-sr.c @@ -21,6 +21,7 @@ #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base) { @@ -34,11 +35,7 @@ static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base) else elrsr1 = 0; -#ifdef CONFIG_CPU_BIG_ENDIAN - cpu_if->vgic_elrsr = ((u64)elrsr0 << 32) | elrsr1; -#else cpu_if->vgic_elrsr = ((u64)elrsr1 << 32) | elrsr0; -#endif } static void __hyp_text save_lrs(struct kvm_vcpu *vcpu, void __iomem *base) diff --git a/virt/kvm/arm/mmio.c b/virt/kvm/arm/mmio.c index b6e715f..dac7ceb 100644 --- a/virt/kvm/arm/mmio.c +++ b/virt/kvm/arm/mmio.c @@ -112,7 +112,7 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) } trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr, - data); + &data); data = vcpu_data_host_to_guest(vcpu, data, len); vcpu_set_reg(vcpu, vcpu->arch.mmio_decode.rt, data); } @@ -182,14 +182,14 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, data = vcpu_data_guest_to_host(vcpu, vcpu_get_reg(vcpu, rt), len); - trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data); + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, &data); kvm_mmio_write_buf(data_buf, len, data); ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, fault_ipa, len, data_buf); } else { trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, len, - fault_ipa, 0); + fault_ipa, NULL); ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_ipa, len, data_buf); diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index b36945d..71dc178 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -509,8 +509,6 @@ static void unmap_hyp_range(pgd_t *pgdp, phys_addr_t start, u64 size) */ void free_hyp_pgds(void) { - unsigned long addr; - mutex_lock(&kvm_hyp_pgd_mutex); if (boot_hyp_pgd) { @@ -521,10 +519,10 @@ void free_hyp_pgds(void) if (hyp_pgd) { unmap_hyp_range(hyp_pgd, hyp_idmap_start, PAGE_SIZE); - for (addr = PAGE_OFFSET; virt_addr_valid(addr); addr += PGDIR_SIZE) - unmap_hyp_range(hyp_pgd, kern_hyp_va(addr), PGDIR_SIZE); - for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE) - unmap_hyp_range(hyp_pgd, kern_hyp_va(addr), PGDIR_SIZE); + unmap_hyp_range(hyp_pgd, kern_hyp_va(PAGE_OFFSET), + (uintptr_t)high_memory - PAGE_OFFSET); + unmap_hyp_range(hyp_pgd, kern_hyp_va(VMALLOC_START), + VMALLOC_END - VMALLOC_START); free_pages((unsigned long)hyp_pgd, hyp_pgd_order); hyp_pgd = NULL; @@ -926,6 +924,25 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache return 0; } +static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr) +{ + pmd_t *pmdp; + pte_t *ptep; + + pmdp = stage2_get_pmd(kvm, NULL, addr); + if (!pmdp || pmd_none(*pmdp) || !pmd_present(*pmdp)) + return false; + + if (pmd_thp_or_huge(*pmdp)) + return kvm_s2pmd_exec(pmdp); + + ptep = pte_offset_kernel(pmdp, addr); + if (!ptep || pte_none(*ptep) || !pte_present(*ptep)) + return false; + + return kvm_s2pte_exec(ptep); +} + static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, phys_addr_t addr, const pte_t *new_pte, unsigned long flags) @@ -1257,10 +1274,14 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); } -static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, kvm_pfn_t pfn, - unsigned long size) +static void clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size) { - __coherent_cache_guest_page(vcpu, pfn, size); + __clean_dcache_guest_page(pfn, size); +} + +static void invalidate_icache_guest_page(kvm_pfn_t pfn, unsigned long size) +{ + __invalidate_icache_guest_page(pfn, size); } static void kvm_send_hwpoison_signal(unsigned long address, @@ -1286,7 +1307,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, unsigned long fault_status) { int ret; - bool write_fault, writable, hugetlb = false, force_pte = false; + bool write_fault, exec_fault, writable, hugetlb = false, force_pte = false; unsigned long mmu_seq; gfn_t gfn = fault_ipa >> PAGE_SHIFT; struct kvm *kvm = vcpu->kvm; @@ -1298,7 +1319,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, unsigned long flags = 0; write_fault = kvm_is_write_fault(vcpu); - if (fault_status == FSC_PERM && !write_fault) { + exec_fault = kvm_vcpu_trap_is_iabt(vcpu); + VM_BUG_ON(write_fault && exec_fault); + + if (fault_status == FSC_PERM && !write_fault && !exec_fault) { kvm_err("Unexpected L2 read permission error\n"); return -EFAULT; } @@ -1312,7 +1336,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return -EFAULT; } - if (is_vm_hugetlb_page(vma) && !logging_active) { + if (vma_kernel_pagesize(vma) == PMD_SIZE && !logging_active) { hugetlb = true; gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT; } else { @@ -1391,7 +1415,19 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, new_pmd = kvm_s2pmd_mkwrite(new_pmd); kvm_set_pfn_dirty(pfn); } - coherent_cache_guest_page(vcpu, pfn, PMD_SIZE); + + if (fault_status != FSC_PERM) + clean_dcache_guest_page(pfn, PMD_SIZE); + + if (exec_fault) { + new_pmd = kvm_s2pmd_mkexec(new_pmd); + invalidate_icache_guest_page(pfn, PMD_SIZE); + } else if (fault_status == FSC_PERM) { + /* Preserve execute if XN was already cleared */ + if (stage2_is_exec(kvm, fault_ipa)) + new_pmd = kvm_s2pmd_mkexec(new_pmd); + } + ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd); } else { pte_t new_pte = pfn_pte(pfn, mem_type); @@ -1401,7 +1437,19 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, kvm_set_pfn_dirty(pfn); mark_page_dirty(kvm, gfn); } - coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE); + + if (fault_status != FSC_PERM) + clean_dcache_guest_page(pfn, PAGE_SIZE); + + if (exec_fault) { + new_pte = kvm_s2pte_mkexec(new_pte); + invalidate_icache_guest_page(pfn, PAGE_SIZE); + } else if (fault_status == FSC_PERM) { + /* Preserve execute if XN was already cleared */ + if (stage2_is_exec(kvm, fault_ipa)) + new_pte = kvm_s2pte_mkexec(new_pte); + } + ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags); } diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index 6231012..743ca5c 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -285,9 +285,11 @@ int vgic_init(struct kvm *kvm) if (ret) goto out; - ret = vgic_v4_init(kvm); - if (ret) - goto out; + if (vgic_has_its(kvm)) { + ret = vgic_v4_init(kvm); + if (ret) + goto out; + } kvm_for_each_vcpu(i, vcpu, kvm) kvm_vgic_vcpu_enable(vcpu); diff --git a/virt/kvm/arm/vgic/vgic-irqfd.c b/virt/kvm/arm/vgic/vgic-irqfd.c index b7baf58..99e026d 100644 --- a/virt/kvm/arm/vgic/vgic-irqfd.c +++ b/virt/kvm/arm/vgic/vgic-irqfd.c @@ -112,8 +112,7 @@ int kvm_vgic_setup_default_irq_routing(struct kvm *kvm) u32 nr = dist->nr_spis; int i, ret; - entries = kcalloc(nr, sizeof(struct kvm_kernel_irq_routing_entry), - GFP_KERNEL); + entries = kcalloc(nr, sizeof(*entries), GFP_KERNEL); if (!entries) return -ENOMEM; diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 1f761a9..4650953 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -421,6 +421,7 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) u32 *intids; int nr_irqs, i; unsigned long flags; + u8 pendmask; nr_irqs = vgic_copy_lpi_list(vcpu, &intids); if (nr_irqs < 0) @@ -428,7 +429,6 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) for (i = 0; i < nr_irqs; i++) { int byte_offset, bit_nr; - u8 pendmask; byte_offset = intids[i] / BITS_PER_BYTE; bit_nr = intids[i] % BITS_PER_BYTE; @@ -821,6 +821,8 @@ static int vgic_its_alloc_collection(struct vgic_its *its, return E_ITS_MAPC_COLLECTION_OOR; collection = kzalloc(sizeof(*collection), GFP_KERNEL); + if (!collection) + return -ENOMEM; collection->collection_id = coll_id; collection->target_addr = COLLECTION_NOT_MAPPED; @@ -1032,10 +1034,8 @@ static int vgic_its_cmd_handle_mapd(struct kvm *kvm, struct vgic_its *its, device = vgic_its_alloc_device(its, device_id, itt_addr, num_eventid_bits); - if (IS_ERR(device)) - return PTR_ERR(device); - return 0; + return PTR_ERR_OR_ZERO(device); } /* diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index deb51ee..83d82bd 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -16,6 +16,7 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> #include <kvm/iodev.h> +#include <kvm/arm_arch_timer.h> #include <kvm/arm_vgic.h> #include "vgic.h" @@ -122,10 +123,43 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, return value; } +/* + * This function will return the VCPU that performed the MMIO access and + * trapped from within the VM, and will return NULL if this is a userspace + * access. + * + * We can disable preemption locally around accessing the per-CPU variable, + * and use the resolved vcpu pointer after enabling preemption again, because + * even if the current thread is migrated to another CPU, reading the per-CPU + * value later will give us the same value as we update the per-CPU variable + * in the preempt notifier handlers. + */ +static struct kvm_vcpu *vgic_get_mmio_requester_vcpu(void) +{ + struct kvm_vcpu *vcpu; + + preempt_disable(); + vcpu = kvm_arm_get_running_vcpu(); + preempt_enable(); + return vcpu; +} + +/* Must be called with irq->irq_lock held */ +static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, + bool is_uaccess) +{ + if (is_uaccess) + return; + + irq->pending_latch = true; + vgic_irq_set_phys_active(irq, true); +} + void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { + bool is_uaccess = !vgic_get_mmio_requester_vcpu(); u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; @@ -134,17 +168,45 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); spin_lock_irqsave(&irq->irq_lock, flags); - irq->pending_latch = true; - + if (irq->hw) + vgic_hw_irq_spending(vcpu, irq, is_uaccess); + else + irq->pending_latch = true; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } } +/* Must be called with irq->irq_lock held */ +static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, + bool is_uaccess) +{ + if (is_uaccess) + return; + + irq->pending_latch = false; + + /* + * We don't want the guest to effectively mask the physical + * interrupt by doing a write to SPENDR followed by a write to + * CPENDR for HW interrupts, so we clear the active state on + * the physical side if the virtual interrupt is not active. + * This may lead to taking an additional interrupt on the + * host, but that should not be a problem as the worst that + * can happen is an additional vgic injection. We also clear + * the pending state to maintain proper semantics for edge HW + * interrupts. + */ + vgic_irq_set_phys_pending(irq, false); + if (!irq->active) + vgic_irq_set_phys_active(irq, false); +} + void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { + bool is_uaccess = !vgic_get_mmio_requester_vcpu(); u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; @@ -154,7 +216,10 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, spin_lock_irqsave(&irq->irq_lock, flags); - irq->pending_latch = false; + if (irq->hw) + vgic_hw_irq_cpending(vcpu, irq, is_uaccess); + else + irq->pending_latch = false; spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); @@ -181,27 +246,24 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, return value; } +/* Must be called with irq->irq_lock held */ +static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, + bool active, bool is_uaccess) +{ + if (is_uaccess) + return; + + irq->active = active; + vgic_irq_set_phys_active(irq, active); +} + static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - bool new_active_state) + bool active) { - struct kvm_vcpu *requester_vcpu; unsigned long flags; - spin_lock_irqsave(&irq->irq_lock, flags); + struct kvm_vcpu *requester_vcpu = vgic_get_mmio_requester_vcpu(); - /* - * The vcpu parameter here can mean multiple things depending on how - * this function is called; when handling a trap from the kernel it - * depends on the GIC version, and these functions are also called as - * part of save/restore from userspace. - * - * Therefore, we have to figure out the requester in a reliable way. - * - * When accessing VGIC state from user space, the requester_vcpu is - * NULL, which is fine, because we guarantee that no VCPUs are running - * when accessing VGIC state from user space so irq->vcpu->cpu is - * always -1. - */ - requester_vcpu = kvm_arm_get_running_vcpu(); + spin_lock_irqsave(&irq->irq_lock, flags); /* * If this virtual IRQ was written into a list register, we @@ -213,14 +275,23 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, * vgic_change_active_prepare) and still has to sync back this IRQ, * so we release and re-acquire the spin_lock to let the other thread * sync back the IRQ. + * + * When accessing VGIC state from user space, requester_vcpu is + * NULL, which is fine, because we guarantee that no VCPUs are running + * when accessing VGIC state from user space so irq->vcpu->cpu is + * always -1. */ while (irq->vcpu && /* IRQ may have state in an LR somewhere */ irq->vcpu != requester_vcpu && /* Current thread is not the VCPU thread */ irq->vcpu->cpu != -1) /* VCPU thread is running */ cond_resched_lock(&irq->irq_lock); - irq->active = new_active_state; - if (new_active_state) + if (irq->hw) + vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu); + else + irq->active = active; + + if (irq->active) vgic_queue_irq_unlock(vcpu->kvm, irq, flags); else spin_unlock_irqrestore(&irq->irq_lock, flags); diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c index 8089710..c32d7b9 100644 --- a/virt/kvm/arm/vgic/vgic-v2.c +++ b/virt/kvm/arm/vgic/vgic-v2.c @@ -105,6 +105,26 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) irq->pending_latch = false; } + /* + * Level-triggered mapped IRQs are special because we only + * observe rising edges as input to the VGIC. + * + * If the guest never acked the interrupt we have to sample + * the physical line and set the line level, because the + * device state could have changed or we simply need to + * process the still pending interrupt later. + * + * If this causes us to lower the level, we have to also clear + * the physical active state, since we will otherwise never be + * told when the interrupt becomes asserted again. + */ + if (vgic_irq_is_mapped_level(irq) && (val & GICH_LR_PENDING_BIT)) { + irq->line_level = vgic_get_phys_line_level(irq); + + if (!irq->line_level) + vgic_irq_set_phys_active(irq, false); + } + spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } @@ -162,6 +182,15 @@ void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr) val |= GICH_LR_EOI; } + /* + * Level-triggered mapped IRQs are special because we only observe + * rising edges as input to the VGIC. We therefore lower the line + * level here, so that we can take new virtual IRQs. See + * vgic_v2_fold_lr_state for more info. + */ + if (vgic_irq_is_mapped_level(irq) && (val & GICH_LR_PENDING_BIT)) + irq->line_level = false; + /* The GICv2 LR only holds five bits of priority. */ val |= (irq->priority >> 3) << GICH_LR_PRIORITY_SHIFT; diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 2f05f732..6b32941 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -96,6 +96,26 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) irq->pending_latch = false; } + /* + * Level-triggered mapped IRQs are special because we only + * observe rising edges as input to the VGIC. + * + * If the guest never acked the interrupt we have to sample + * the physical line and set the line level, because the + * device state could have changed or we simply need to + * process the still pending interrupt later. + * + * If this causes us to lower the level, we have to also clear + * the physical active state, since we will otherwise never be + * told when the interrupt becomes asserted again. + */ + if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) { + irq->line_level = vgic_get_phys_line_level(irq); + + if (!irq->line_level) + vgic_irq_set_phys_active(irq, false); + } + spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } @@ -146,6 +166,15 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr) } /* + * Level-triggered mapped IRQs are special because we only observe + * rising edges as input to the VGIC. We therefore lower the line + * level here, so that we can take new virtual IRQs. See + * vgic_v3_fold_lr_state for more info. + */ + if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) + irq->line_level = false; + + /* * We currently only support Group1 interrupts, which is a * known defect. This needs to be addressed at some point. */ @@ -327,13 +356,13 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) int last_byte_offset = -1; struct vgic_irq *irq; int ret; + u8 val; list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { int byte_offset, bit_nr; struct kvm_vcpu *vcpu; gpa_t pendbase, ptr; bool stored; - u8 val; vcpu = irq->target_vcpu; if (!vcpu) diff --git a/virt/kvm/arm/vgic/vgic-v4.c b/virt/kvm/arm/vgic/vgic-v4.c index 53c324a..bc42651 100644 --- a/virt/kvm/arm/vgic/vgic-v4.c +++ b/virt/kvm/arm/vgic/vgic-v4.c @@ -118,7 +118,7 @@ int vgic_v4_init(struct kvm *kvm) struct kvm_vcpu *vcpu; int i, nr_vcpus, ret; - if (!vgic_supports_direct_msis(kvm)) + if (!kvm_vgic_global_state.has_gicv4) return 0; /* Nothing to see here... move along. */ if (dist->its_vm.vpes) @@ -337,8 +337,10 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq, goto out; WARN_ON(!(irq->hw && irq->host_irq == virq)); - irq->hw = false; - ret = its_unmap_vlpi(virq); + if (irq->hw) { + irq->hw = false; + ret = its_unmap_vlpi(virq); + } out: mutex_unlock(&its->its_lock); diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index b168a32..c7c5ef1 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -144,6 +144,38 @@ void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) kfree(irq); } +void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending) +{ + WARN_ON(irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + pending)); +} + +bool vgic_get_phys_line_level(struct vgic_irq *irq) +{ + bool line_level; + + BUG_ON(!irq->hw); + + if (irq->get_input_level) + return irq->get_input_level(irq->intid); + + WARN_ON(irq_get_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + &line_level)); + return line_level; +} + +/* Set/Clear the physical active state */ +void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active) +{ + + BUG_ON(!irq->hw); + WARN_ON(irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_ACTIVE, + active)); +} + /** * kvm_vgic_target_oracle - compute the target vcpu for an irq * @@ -413,7 +445,8 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid, /* @irq->irq_lock must be held */ static int kvm_vgic_map_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - unsigned int host_irq) + unsigned int host_irq, + bool (*get_input_level)(int vindid)) { struct irq_desc *desc; struct irq_data *data; @@ -433,6 +466,7 @@ static int kvm_vgic_map_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq, irq->hw = true; irq->host_irq = host_irq; irq->hwintid = data->hwirq; + irq->get_input_level = get_input_level; return 0; } @@ -441,10 +475,11 @@ static inline void kvm_vgic_unmap_irq(struct vgic_irq *irq) { irq->hw = false; irq->hwintid = 0; + irq->get_input_level = NULL; } int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq, - u32 vintid) + u32 vintid, bool (*get_input_level)(int vindid)) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, vintid); unsigned long flags; @@ -453,7 +488,7 @@ int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq, BUG_ON(!irq); spin_lock_irqsave(&irq->irq_lock, flags); - ret = kvm_vgic_map_irq(vcpu, irq, host_irq); + ret = kvm_vgic_map_irq(vcpu, irq, host_irq, get_input_level); spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); @@ -492,6 +527,7 @@ int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid) int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsigned int intid, void *owner) { struct vgic_irq *irq; + unsigned long flags; int ret = 0; if (!vgic_initialized(vcpu->kvm)) @@ -502,12 +538,12 @@ int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsigned int intid, void *owner) return -EINVAL; irq = vgic_get_irq(vcpu->kvm, vcpu, intid); - spin_lock(&irq->irq_lock); + spin_lock_irqsave(&irq->irq_lock, flags); if (irq->owner && irq->owner != owner) ret = -EEXIST; else irq->owner = owner; - spin_unlock(&irq->irq_lock); + spin_unlock_irqrestore(&irq->irq_lock, flags); return ret; } @@ -823,13 +859,14 @@ void vgic_kick_vcpus(struct kvm *kvm) bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, vintid); + struct vgic_irq *irq; bool map_is_active; unsigned long flags; if (!vgic_initialized(vcpu->kvm)) return false; + irq = vgic_get_irq(vcpu->kvm, vcpu, vintid); spin_lock_irqsave(&irq->irq_lock, flags); map_is_active = irq->hw && irq->active; spin_unlock_irqrestore(&irq->irq_lock, flags); diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index efbcf8f..12c37b8 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -104,6 +104,11 @@ static inline bool irq_is_pending(struct vgic_irq *irq) return irq->pending_latch || irq->line_level; } +static inline bool vgic_irq_is_mapped_level(struct vgic_irq *irq) +{ + return irq->config == VGIC_CONFIG_LEVEL && irq->hw; +} + /* * This struct provides an intermediate representation of the fields contained * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC @@ -140,6 +145,9 @@ vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 intid); void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq); +bool vgic_get_phys_line_level(struct vgic_irq *irq); +void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending); +void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active); bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq, unsigned long flags); void vgic_kick_vcpus(struct kvm *kvm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index c422c10..8a937b7 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -135,6 +135,11 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm); static unsigned long long kvm_createvm_count; static unsigned long long kvm_active_vms; +__weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, + unsigned long start, unsigned long end) +{ +} + bool kvm_is_reserved_pfn(kvm_pfn_t pfn) { if (pfn_valid(pfn)) @@ -146,17 +151,12 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn) /* * Switches to specified vcpu, until a matching vcpu_put() */ -int vcpu_load(struct kvm_vcpu *vcpu) +void vcpu_load(struct kvm_vcpu *vcpu) { - int cpu; - - if (mutex_lock_killable(&vcpu->mutex)) - return -EINTR; - cpu = get_cpu(); + int cpu = get_cpu(); preempt_notifier_register(&vcpu->preempt_notifier); kvm_arch_vcpu_load(vcpu, cpu); put_cpu(); - return 0; } EXPORT_SYMBOL_GPL(vcpu_load); @@ -166,7 +166,6 @@ void vcpu_put(struct kvm_vcpu *vcpu) kvm_arch_vcpu_put(vcpu); preempt_notifier_unregister(&vcpu->preempt_notifier); preempt_enable(); - mutex_unlock(&vcpu->mutex); } EXPORT_SYMBOL_GPL(vcpu_put); @@ -360,6 +359,9 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, kvm_flush_remote_tlbs(kvm); spin_unlock(&kvm->mmu_lock); + + kvm_arch_mmu_notifier_invalidate_range(kvm, start, end); + srcu_read_unlock(&kvm->srcu, idx); } @@ -1426,7 +1428,8 @@ static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault) static int hva_to_pfn_remapped(struct vm_area_struct *vma, unsigned long addr, bool *async, - bool write_fault, kvm_pfn_t *p_pfn) + bool write_fault, bool *writable, + kvm_pfn_t *p_pfn) { unsigned long pfn; int r; @@ -1452,6 +1455,8 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, } + if (writable) + *writable = true; /* * Get a reference here because callers of *hva_to_pfn* and @@ -1517,7 +1522,7 @@ retry: if (vma == NULL) pfn = KVM_PFN_ERR_FAULT; else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) { - r = hva_to_pfn_remapped(vma, addr, async, write_fault, &pfn); + r = hva_to_pfn_remapped(vma, addr, async, write_fault, writable, &pfn); if (r == -EAGAIN) goto retry; if (r < 0) @@ -2410,7 +2415,10 @@ static struct file_operations kvm_vcpu_fops = { */ static int create_vcpu_fd(struct kvm_vcpu *vcpu) { - return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC); + char name[8 + 1 + ITOA_MAX_LEN + 1]; + + snprintf(name, sizeof(name), "kvm-vcpu:%d", vcpu->vcpu_id); + return anon_inode_getfd(name, &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC); } static int kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) @@ -2542,19 +2550,16 @@ static long kvm_vcpu_ioctl(struct file *filp, if (unlikely(_IOC_TYPE(ioctl) != KVMIO)) return -EINVAL; -#if defined(CONFIG_S390) || defined(CONFIG_PPC) || defined(CONFIG_MIPS) /* - * Special cases: vcpu ioctls that are asynchronous to vcpu execution, - * so vcpu_load() would break it. + * Some architectures have vcpu ioctls that are asynchronous to vcpu + * execution; mutex_lock() would break them. */ - if (ioctl == KVM_S390_INTERRUPT || ioctl == KVM_S390_IRQ || ioctl == KVM_INTERRUPT) - return kvm_arch_vcpu_ioctl(filp, ioctl, arg); -#endif - - - r = vcpu_load(vcpu); - if (r) + r = kvm_arch_vcpu_async_ioctl(filp, ioctl, arg); + if (r != -ENOIOCTLCMD) return r; + + if (mutex_lock_killable(&vcpu->mutex)) + return -EINTR; switch (ioctl) { case KVM_RUN: { struct pid *oldpid; @@ -2726,7 +2731,7 @@ out_free1: r = kvm_arch_vcpu_ioctl(filp, ioctl, arg); } out: - vcpu_put(vcpu); + mutex_unlock(&vcpu->mutex); kfree(fpu); kfree(kvm_sregs); return r; @@ -3178,21 +3183,18 @@ static int kvm_dev_ioctl_create_vm(unsigned long type) return PTR_ERR(kvm); #ifdef CONFIG_KVM_MMIO r = kvm_coalesced_mmio_init(kvm); - if (r < 0) { - kvm_put_kvm(kvm); - return r; - } + if (r < 0) + goto put_kvm; #endif r = get_unused_fd_flags(O_CLOEXEC); - if (r < 0) { - kvm_put_kvm(kvm); - return r; - } + if (r < 0) + goto put_kvm; + file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR); if (IS_ERR(file)) { put_unused_fd(r); - kvm_put_kvm(kvm); - return PTR_ERR(file); + r = PTR_ERR(file); + goto put_kvm; } /* @@ -3210,6 +3212,10 @@ static int kvm_dev_ioctl_create_vm(unsigned long type) fd_install(r, file); return r; + +put_kvm: + kvm_put_kvm(kvm); + return r; } static long kvm_dev_ioctl(struct file *filp, |